activity
20172022
most citedGradient tracking and variance reduction for decentralized optimization and machine learning

7 citations · 17 across the 11 of their papers we have counts for

collaborators
Showing 2021Show all

6 papers · 1 filter

math.OC20216 cited

A Stochastic Proximal Gradient Framework for Decentralized Non-Convex Composite Optimization: Topology-Independent Sample Complexity and Communication Efficiency

Ran Xin, Subhro Das, Usman A. Khan +1

Decentralized optimization is a promising parallel computation paradigm for large-scale data analytics and machine learning problems defined over a network of nodes. This paper is…

eess.SY2021

Distributed Detection and Mitigation of Biasing Attacks over Multi-Agent Networks

Mohammadreza Doostmohammadian, Houman Zarrabi, Hamid R. Rabiee +2

This paper proposes a distributed attack detection and mitigation technique based on distributed estimation over a multi-agent network, where the agents take partial system measure…

eess.SY20211 cited

Simultaneous Distributed Estimation and Attack Detection/Isolation in Social Networks: Structural Observability, Kronecker-Product Network, and Chi-Square Detector

Mohammadreza Doostmohammadian, Themistoklis Charalambous, Miadreza Shafie-khah +2

This paper considers distributed estimation of linear systems when the state observations are corrupted with Gaussian noise of unbounded support and under possible random adversari…

eess.SY2021

Distributed support-vector-machine over dynamic balanced directed networks

Mohammadreza Doostmohammadian, Alireza Aghasi, Themistoklis Charalambous +1

In this paper, we consider the binary classification problem via distributed Support-Vector-Machines (SVM), where the idea is to train a network of agents, with limited share of da…

eess.SY2021

Consensus-Based Distributed Estimation in the Presence of Heterogeneous, Time-Invariant Delays

Mohammadreza Doostmohammadian, Usman A. Khan, Mohammad Pirani +1

Classical distributed estimation scenarios typically assume timely and reliable exchanges of information over the sensor network. This paper, in contrast, considers single time-sca…

math.OC2021

A Hybrid Variance-Reduced Method for Decentralized Stochastic Non-Convex Optimization

Ran Xin, Usman A. Khan, Soummya Kar

This paper considers decentralized stochastic optimization over a network of nodes, where each node possesses a smooth non-convex local cost function and the goal of the networ…